Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.8391. Min Act: -0.0000

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.5414. Min Act: -0.0000

Data Index: 1143698 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.4675. Min Act: -0.0000

Data Index: 864292 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.4258. Min Act: -0.0000

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.3856. Min Act: -0.0000

Data Index: 1135440 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.3665. Min Act: -0.0000

Data Index: 99611 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.1895. Min Act: -0.0000

Data Index: 901222 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.1766. Min Act: -0.0000

Data Index: 931090 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.1951. Min Act: -0.0000

Data Index: 634070 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.0890. Min Act: -0.0000

Data Index: 59238 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.0484. Min Act: -0.0000

Data Index: 201143 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.0219. Min Act: -0.0000

Data Index: 1323310 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.0010. Min Act: -0.0001

Data Index: 481009 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 2.8391. Min Range: -2.8391

Max Act: 2.1076. Min Act: -0.0000

Data Index: 862038 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 2.8391. Min Range: -2.8391

Max Act: 1.9797. Min Act: -0.0001

Data Index: 476046 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 2.8391. Min Range: -2.8391

Max Act: 1.9741. Min Act: -0.0000

Data Index: 124600 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 2.8391. Min Range: -2.8391

Max Act: 1.9595. Min Act: -0.0000

Data Index: 331553 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 2.8391. Min Range: -2.8391

Max Act: 1.9419. Min Act: -0.0000

Data Index: 62402 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 2.8391. Min Range: -2.8391

Max Act: 1.6790. Min Act: -0.0000

Data Index: 188713 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 2.8391. Min Range: -2.8391

Max Act: 1.8032. Min Act: -0.0000

Data Index: 512409 (C4 (Web Text))

Max Activating Token Index: 183